The rapid evolution of financial markets and the proliferation of digital financial services have significantly increased the volume and complexity of data generated by investors, institutions, and customers. This transformation has created a critical need for intelligent analytical systems capable of interpreting complex financial signals and customer behavior patterns. Artificial intelligence and machine learning have emerged as powerful tools for addressing this challenge, particularly in the areas of stock market forecasting, risk management, and customer propensity prediction. This research develops a comprehensive conceptual framework for integrating machine learning-based propensity prediction models with decision engine architectures to improve forecasting accuracy and financial decision-making. The study synthesizes insights from financial time-series forecasting, machine learning algorithms, big data analytics, and behavioral finance to construct an advanced predictive decision support system suitable for modern financial institutions.

The research examines multiple predictive techniques including artificial neural networks, support vector machines, hybrid ARIMA models, and rule-based analytical systems that have historically been applied to financial forecasting. Additionally, the study explores the integration of customer-level data analytics with market-level financial indicators to develop decision engines capable of predicting both market movement and investor behavior. Particular attention is given to the role of feature engineering, data preparation, and hybrid modeling strategies in improving predictive accuracy. The study further discusses the importance of fairness, transparency, and ethical considerations in the deployment of machine learning models within financial decision-making processes.

The proposed framework combines predictive modeling techniques with automated decision engines to enable financial institutions to derive actionable insights from complex datasets. The results indicate that hybrid machine learning approaches combined with intelligent decision engines can significantly enhance forecasting reliability and enable proactive financial strategies. The research contributes to the growing body of literature on financial artificial intelligence by providing a comprehensive theoretical model that integrates financial time-series forecasting with customer propensity analytics.

Propensity Prediction, Decision Engine, Financial Forecasting, Machine Learning in Finance

Bianchi, D., Büchner, M., and Tamoni, A. Bond Risk Premiums with Machine Learning. The Review of Financial Studies.

Bilinski, P., Lyssimachou, D., and Walker, M. Target price accuracy: International evidence. The Accounting Review.

Bird, S., Klein, E., and Loper, E. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit. O’Reilly Media.

Blitz, D. Invited Editorial Comment: The Dark Side of Passive Investing. The Journal of Portfolio Management.

Burniske, C., and White, A. Bitcoin: Ringing the Bell for a New Asset Class.

Campbell, S. D., and Sharpe, S. A. Anchoring bias in consensus forecasts and its effect on market prices. Journal of Financial and Quantitative Analysis.

Ciampi, F., Demi, S., Magrini, A., Marzi, G., and Papa, A. Exploring the impact of big data analytics capabilities on business model innovation. Journal of Business Research.

Devriendt, F., Berrevoets, J., and Verbeke, W. Why you should stop predicting customer churn and start using uplift models. Information Sciences.

Du, S., and Xie, C. Paradoxes of artificial intelligence in consumer markets: Ethical challenges and opportunities. Journal of Business Research.

Huang, W., Nakamori, Y., and Wang, S. Forecasting stock market movement direction with support vector machine. Computers & Operations Research.

Huang, C.-L., Tsai, C.-Y., and Hsu, C.-J. A hybrid SOFM-SVR with a filter-based feature selection for stock market forecasting. Expert Systems with Applications.

Hudson, R., Urquhart, A., and Gregoriou, A. Sampling frequency and the performance of different types of technical trading rules. Finance Research Letters.

Kara, Y., Boyacioglu, M. A., and Baykan, O. K. Predicting direction of stock price index movement using artificial neural networks and support vector machines. Expert Systems with Applications.

Kim, K. Financial time series forecasting using support vector machines. Neurocomputing.

Kim, K.-J., and Han, I. Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Systems with Applications.

Krishnan, G., Bhat, A. K., & Shah, J. (2025). Decision engine: Propensity prediction in the financial industry based on customer data features. In Artificial Intelligence and Sustainable Innovation (pp. 107-112). CRC Press.

Kumar, D., Ravi, V., and Karthik, T. Proximal support vector machine based hybrid prediction models for trend forecasting in financial markets. Journal of Computer Science.

Laboissiere, L. A., Fernandes, R. A. S., and Lage, G. G. Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks. Applied Soft Computing.

Makhlouf, K., Zhioua, S., and Palamidessi, C. Machine learning fairness notions: Bridging the gap with real-world applications. Information Processing & Management.

Narayan, P. K., Sharma, S. S., and Phan, D. H. B. Intraday return predictability, portfolio maximisation, and hedging. Emerging Markets Review.

Pai, P.-F., and Lin, C.-S. A hybrid ARIMA and support vector machines model in stock price forecasting. Omega.

Patel, J., Shah, S., Thakkar, P., and Kotecha, K. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Systems with Applications.

Patel, J., Shah, S., Thakkar, P., and Kotecha, K. Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications.

Podsiadlo, M., and Rybinski, H. Financial time series forecasting using rough sets with time-weighted rule voting. Expert Systems with Applications.

Rodríguez-González, A., García-Crespo, Á., Colomo-Palacios, R., and Gómez-Berbís, J. CAST: Using neural networks to improve trading systems based on technical analysis by means of the RSI financial indicator. Expert Systems with Applications.

Sobreiro, V. A., Kimura, H., and Lima, M. V. A. The profitability of moving average trading rules in BRICS and emerging stock markets. The North American Journal of Economics and Finance.

Son, Y., Noh, D., and Lee, J. Forecasting trends of high-frequency KOSPI200 index data using learning classifiers. Expert Systems with Applications.